mihirp1998 / AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆284Updated 6 months ago
Alternatives and similar repositories for AlignProp
Users that are interested in AlignProp are comparing it to the libraries listed below
Sorting:
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆481Updated 3 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆225Updated last year
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆122Updated 4 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆340Updated 7 months ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆255Updated last month
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆136Updated 3 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆284Updated last year
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆247Updated 5 months ago
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆257Updated last year
- GenEval: An object-focused framework for evaluating text-to-image alignment☆270Updated 2 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆292Updated 6 months ago
- MoVQGAN - model for the image encoding and reconstruction☆233Updated last year
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆335Updated 10 months ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆237Updated last month
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆221Updated 2 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆275Updated 2 months ago
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆112Updated 7 months ago
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆275Updated 5 months ago
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆206Updated last month
- An implementation of the Prompt-to-Prompt paper for the SDXL architecture☆110Updated 11 months ago
- [CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation☆278Updated last year
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆130Updated 10 months ago
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆167Updated 2 months ago
- ☆122Updated 10 months ago
- Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆194Updated last month
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆506Updated 11 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. (ICLR 2024)☆168Updated last month
- Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"☆235Updated 10 months ago
- "FreeU: Free Lunch in Diffusion U-Net" for Huggingface Diffusers☆100Updated last year
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆404Updated last year